Gide: Graphical Image Deblurring Exploration

Author

Cash, Brianna R. ; O´Leary, Dianne P.

Volume

17

Issue

3

fYear

2015

fDate

May-June 2015

Firstpage

62

Lastpage

67

Abstract

A Matlab tool called GIDE allows user-aided deblurring of images. GIDE helps practitioners restore a blurred grayscale image using their knowledge or intuition about the true image. At the same time, it safeguards from possible bias by validating the choice using statistical diagnostics, based on an assumption of Gaussian added noise. GIDE also allows practitioners (or students) to visually explore the range of statistically likely solutions resulting from any of three regularization methods: Tikhonov, truncated SVD, and total variation.

Keywords

Gaussian noise; image restoration; singular value decomposition; statistical analysis; GIDE; Gaussian added noise; Matlab tool; Tikhonov; blurred grayscale image; graphical image deblurring exploration; regularization methods; statistical diagnostics; total variation; truncated SVD; user-aided image deblurring; Gaussian processes; Image processing; Matlab; Noise measurement; Scientific computing; Statisical analysis; Deblurring; Gaussian noise; graphics; images; scientific computing; statistical noise;

fLanguage

English

Journal_Title

Computing in Science & Engineering

Publisher

ieee

ISSN

1521-9615

Type

jour

DOI

10.1109/MCSE.2015.51

Filename

7091795